atlassian_vulnerability_check
ChatGPTCheck an Atlassian Data Center instance for CVE-2026-21589 Passively read the version a visitor-supplied domain, IP or URL prints on its public sign-in page or application-link manifest (Confluence, Jira, Bitbucket, Bamboo, Crowd, Fisheye, Crucible) and report whether it falls in the affected range of CVE-2026-21589 (Atlassian CVSS 9.3). Ordinary GETs of public pages, never sends an exploit request and requests no file from the web root. Returns the verdict synchronously.
get_cve
ChatGPTRead one CVE from the Atlas catalogue by id (for example CVE-2023-40044): its description, scores, references and related CVEs of the same product. Use it when the user names a CVE or picks one from search_cves.
get_domain_scan
ChatGPTRead an Atlas domain risk scan by its id: its status and, once completed, the full result. Use it to follow up on a scan_domain call that returned before the scan finished. Scan links expire after a few days.
gitlab_vulnerability_check
ChatGPTCheck a GitLab instance for CVE-2026-110264 Passively read the GitLab release a visitor-supplied domain, IP or URL shows on its public sign-in page and report whether it falls in the affected range of CVE-2026-110264 (CVSS 10.0). Ordinary GETs of one public page, never sends an exploit request. Returns the verdict synchronously.
netscaler_vulnerability_check
ChatGPTCheck a NetScaler for CTX697096 exposure Passively fingerprint the firmware build of a visitor-supplied NetScaler ADC / Gateway (by domain, IP, or URL) and report whether it predates the CTX697096 fix (CVE-2026-88771 / CVE-2026-88772). Reads only public pages and resources, never sends an exploit request. Returns the verdict synchronously.
nodejs_vulnerability_check
ChatGPTCheck a version against Node2Shell / HTTP2Shell Compare the output of node -v, or an exact Docker image tag, with the Node.js security release of 21 Oct 2026 for Node2Shell (CVE-2026-111497) and return a firm verdict. The optional stack field (default nodejs) switches to the same flaw, called HTTP2Shell, in the Brotli library, Bun, Python, Ruby, Envoy, ngx_brotli or Debian. An optional Express version adds an exposure note and never changes the verdict. Pure version comparison: no request is made to any server.
php_vulnerability_check
ChatGPTCheck a site for PHP2Shell exposure Passively read the PHP version a visitor-supplied domain, IP or URL advertises in its response headers and report whether it falls in the PHP2Shell affected range (CVE-2026-109618 / CVE-2026-109619). A single GET of the public homepage, never sends an exploit request. Returns the verdict synchronously.
request_full_report
ChatGPTAsk Brandefense to e-mail the full Atlas domain risk report for a domain, the same request as the report form on the Atlas website. The report goes only to a work e-mail address on the scanned domain; personal webmail is refused. Before calling, show the user this consent text and the privacy policy, and set consent=true only if they agree: "I agree to receive the report and related communications from Brandefense. You can unsubscribe at any time. See our Privacy Policy." Privacy Policy: https://brandefense.io/privacy-policy/. Requests are limited per connection per day, and a refused request still counts.
scan_domain
ChatGPTRun an Atlas domain risk scan: how exposed an organisation's domain is across breached credentials, infected devices, dark web and dark chat mentions, phishing look-alikes, exposed documents and data sales, with letter grades and an overall score. Use it when the user asks how risky, exposed or breached a company or domain is. Waits up to about 90 seconds for the result; if the scan is still running, call get_domain_scan with the returned id later. A repeat scan of the same domain returns the recent result (reused=true) and costs nothing, unless that result came back degraded (some sources failed): then a fresh scan runs and is counted. Fresh scans are limited per rolling 24 hours, and fresh_scans_left_today says how many remain.
search_cves
ChatGPTSearch the Atlas CVE catalogue: the vulnerabilities Atlas tracks, with severity, CVSS and EPSS scores and whether they are known to be exploited (KEV). Use it when the user asks about vulnerabilities in a product or vendor, or wants the most urgent ones. q matches CVE id, vendor, product and title (every word must match); severity is one of info, low, medium, high, critical. Results are most urgent first.
wordpress_exposure
ChatGPTCheck a site for wp2shell exposure Passively fingerprint the WordPress version of a visitor-supplied domain or URL and report whether it falls in the wp2shell affected range (CVE-2026-63030 / CVE-2026-60137). Reads only the target's public readme and homepage, never sends an exploit request. Returns the verdict synchronously.
atlassian_vulnerability_check
Claudeget_cve
Claudeget_domain_scan
Claudegitlab_vulnerability_check
Claudenetscaler_vulnerability_check
Claudenodejs_vulnerability_check
Claudephp_vulnerability_check
Clauderequest_full_report
Claudescan_domain
Claudesearch_cves
Claudewordpress_exposure
Claude